© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125816
    Prev
    Next
    INDEX
    Explanations

    keywords related to permissions and restrictions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onto
    -0.08
    upply
    -0.07
    zan
    -0.07
    inker
    -0.07
    wyn
    -0.07
    Ậ
    -0.07
    Äįan
    -0.07
    eniz
    -0.06
    .Accessible
    -0.06
    ugg
    -0.06
    POSITIVE LOGITS
     further
    0.08
    ded
    0.06
    /stdc
    0.06
     sw
    0.06
    ed
    0.06
    055
    0.06
    epad
    0.06
     super
    0.06
     pap
    0.05
     hepat
    0.05
    Activations Density 0.002%

    No Known Activations